Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    public method declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related keywords or symbols

    np_acts-logits-general · gemini-2.0-flash

    programming, math, and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.47
    text
    -0.46
    -
    -0.43
    <eos>
    -0.43
    ...
    -0.42
     innehå
    -0.42
    ----------------
    -0.41
     raisons
    -0.41
     tamaño
    -0.40
     
    -0.40
    POSITIVE LOGITS
     المعيارى
    1.00
    principalTable
    0.99
     transférez
    0.95
     INTERESAR
    0.92
    BeginContext
    0.88
     كومونز
    0.87
    __':
    0.85
    '])->
    0.81
    SBATCH
    0.80
    WEBPACK
    0.77
    Act Density 0.059%

    No Known Activations